• Gathered from the National Bureau of Economic Research, who creates and distributes a dataset of US mortality for every year since 1959
• Each row represents a single death, while each column represents a different demographic characteristic of the deceased.
• Used the 2019 edition of the dataset since we did not want to focus on COVID-19
• Important information includes education, sex, age classification, day of month, place of death, weekday, manner of death, cause of death, and different ailments for each deceased individual

• Using Behavioral Risk Factor Surveillance System Survey
• Includes different free text survey questions from across the United States and territories with responses broken out by subgroup
  • Includes questions on demographic characteristics, plus queries on current health behaviors, such as tobacco use and seatbelt use
• Combined the secondary dataset by matching up subgroups between the death dataset and the risk factor dataset
  • Tried to use aggregate statistics to analyze how risk factors can be matched with causes of death. ## Given someone is dead, how did they die?
• Since we know that all of the people accounted for in this data are dead, we want to see if we can examine factors such as an individual’s:
  • Age
  • Gender
  • Place of death
  • Educational Level
  • Health Conditions
  • Race

• What specific factors mentioned previously are correlated with higher death rates.

80%

TODO: fix random forest. 80%